Exhibits: Hypothesis Testing

Q1.A Company manufacturing a certain types of breakfast cereals claims that 60% of all
housewives prefer that types to any other. A random sample of 300 housewives contains
165 who do prefer that type. At 5% significance is it true percentage as the company
claims or lower.
Q2.An auditor claims that 10% of company’s invoices are incorrect. To test this claim a
random sample of 200 invoices is checked and 24 are found to be incorrect. Test at the 1%
significant level if auditor’s claim is supported by sample evidence.
Q3.A packaging device is set to fill detergent packed with a mean weight of 150 g. The
standard deviation is known to be 5g. It is important to check the machine periodically
because if it is overfilling it increases the cost of materials, where as if it is under filling the
firm is liable to prosecution. A random sample of 25 filled boxes is taken and weighed,
given a mean net weight of 152.5g. Can we conclude that the machine is no longer
producing the mean weight of 150g?
Q4. The mean and standard deviation of weights produced by the packaging device set to fill
detergent packets with mean weight of 150g, are known to drift upwards due to wearing
of some bearing over time. Obviously it cannot be allowed to drift too far, so a large
sample of 25 boxes is taken and the content weighed. The sample has a mean weight of
151.0g and a S.D of 6.0 g. Use a 5% significance level.
Please do your solution in the space given below
Q5. The personnel department of a company has developed an aptitude test for screening
potential employees. The person who devised the test asserted that the mean mark
attained would be 100. The following results were obtained with a random sample of
applicants, sample mean =96, SD=5.2, n =13 test the hypothesis that the mean mark is
100 against the alternative that mean mark is less than 100, at 1% level.
Q6. A retailing company wishes to know whether there is any difference between the average
size of customer account in it Leeds and Bradford stores. Past experience has shown that
S.D. of the two stores is $16 and $20 respectively. A sample of 100 accounts taken from
each branch gave mean value of $66.20 and $70.40 respectively. Does this provide
evidence at 5% significance, that the mean account size at the two branches in different.
Q7. Firm A claims that it pays it clerical staff on an average at least $10 per week more than
its rival, Firm B. Firm B disputes the claim so each company examines a random sample of
the salaries paid to their workers with the following results.
Firm A: mean = $343.00 S.D.= $13.20 n = 40
Firm B: mean = $338.50 S.D. = $14.30 n =50
What conclusion can be drawn from this evidence at 5% level of significance?
Q8. A training manager wishes to see if there has been any alteration in ability of his trainees
after they have been on a course. The trainees take an aptitude test before they start the
course and an equivalent one after they have completed it; the stores are recorded in
table below. Has any change taken place at 5% significance level?
Trainees: A B C D E F G H I
Before: 74 69 45 67 67 42 54 67 76
After: 69 76 56 59 78 63 54 76 75
Please do your solution in the space given below
Please do your solution in the space given below
CASE-Hypothesis Testing
A large company was about to introduce a new training course for office recruits. 74% of the
previous trainees had passed the aptitude test taken after the end of the pervious course and
the company hoped that the new course would produce a better pass rate. The pass mark for
the test is 60%.
During the first month with the new test a random selection of 18 candidates were each given a
standard test before training and a similar one after training so that their progress could be
monitored. These results are given in Table below:
Trainee A B C D E F G H I
Before 42 56 64 57 45 43 62 51 39
After 56 73 87 68 59 62 79 62 60

Trainee J K L M N O P Q R
Before 64 43 42 62 39 56 57 45 51
After 87 62 56 79 60 73 68 59 62

A random selection of 50 results later in the year gave a pass rate of 84%
We shall use this data to test the following hypotheses:
 The pass rate has improved at the 1% significance level
 The average mark after training is 75%, using α = 0.05
 The average increase in marks is more than 10%, using α = 0.01
 If the data were not paired, the increase in mean marks would be more than 10% using
α =0.01.

Question : A clinical psychologist wishes to test three methods (A, B, C) for reducing hostility
levels in university students to see if there is any real difference between the methods. A
certain psychological test (HLT) was used to measure the degree of hostility (higher scores
indicate greater hostility). Eleven students participated in the experiment and the results are
shown in the table below:
score method gender
1 75.00 A MALE
2 83.00 A FEMALE
3 78.00 A MALE
4 68.00 A FEMALE
5 83.00 A MALE
6 54.00 B FEMALE
7 78.00 B MALE
8 71.00 B FEMALE
9 82.00 C MALE
10 95.00 C FEMALE
11 88.00 C MALE
Exhibit: Chi- Square

If the variance of the filling process is too high, however, the machine is out of control and
needs to be repaired. Therefore, from time to time regular checks of the variance of the
filling process are made. This is done by randomly sampling filled cans, measuring their
amounts, computing the sample variance. A random sample of 30 cans give an estimate of
s2= 18540. Find whether the population variance is maintained to 11500.

(1) A company is interested in determining whether an association exists between the

commuting time of their employees and the level of stress-related problems observed on
job. A study of 116 assembly- line workers revealed the following:
Commuting Stress
Time High Moderate Low Total
Under 20 min. 9 5 18 32
20-50 min. 17 8 28 53
Over 50 min. 18 6 7 31
Total 44 19 53 116
At 1% level of significance, is there any evidence of significant relationship between
commuting time and stress?
(2) A personnel manager is interested in trying to determine whether absenteeism is greater on
one day of the week than on other. His records for the past year show the following
distribution:
Day of week: Mon. Tue. Wed. Thru. Friday
No. of Absentees: 66 56 54 48 75
Test whether the absence is uniformly distributed over the week.
(3) The figures given below are (a) the theoretical frequencies of a distribution, and (b) the
frequencies of a normal distribution having the same mean, standard deviation, and the
total frequency as in (a):
(a) 1 5 20 28 42 22 15 5 2
(b) 1 6 18 25 40 25 18 6 1
Do you think normal distribution provides a good fit to the data?

Please do your solution in the space given below

Please do your solution in the space given below
 Exhibit: Hypothesis testing: correlation coefficient

Find out the correlation between the expenses on advertisement and the sales generated for a
particular FMCG product using the data in the following table:

Advt. Expense (y) Sales Generated (x)

(in Lakhs) (in Lakhs)
5.22 94.2
8.13 69.3
6.52 115.3
4.16 83.3
8.98 85.4
3.05 68.1
3.49 50.7
5.40 96.2
2.39 76.1
2.71 52.0
3.97 82.1
7.56 81.3
5.17 95.7
7.22 83.1
10.08 85.5
6.20 66.3
8.39 74.4
4.08 60.4
6.90 81.2
6.05 83.5
4.76 94.5
2.87 80.1
7.21 76.9
7.06 75.1

Test the significance of the correlation at 5%.

Please do your solution in the space given below

ANSWERS OF EXERCISE ON CONFIDENCE INTERVALS AND HYPOTHESIS TESTING:

Problem Results Comment

No.
6.1 a) 27.6< <29
b) 27.4<<29.2
c) 27.1<<29.5
6.2 26.10<<30.10

6.3 0.979<<1.043

6.4 63.1%< < 70.2%

6.5 Firm A: 338.90<<347.10 Firm B: 335.40<<342.50 Overlap, so could be

same, Firm B is correct
6.6 -0.104<<0.722 Zero excluded so no difference
between methods
6.7 12.7<<15.3 and 15.7<<20.3 No overlap two different population
means
6.8 -2.1<d<12.1 Training may not be effective

6.9 62.2%< <73.8% 75% outside range so claim not

upheld
6.10 92.9%<<99.1% Claim not upheld, mark lower than
100
Hypothesis testing.

7.1 CV = 1.64 TS= 1.94 H0 rejected, mean less than £ 95

7.2 CV = 1.64 TS = 4.63 H0 rejected, she does not spend

longer
7.3 CV = 1.81 TS= 4.38 H0 rejected, mean weight more than
1 kg
7.4 CV = 2.58 TS= 1.58 H0 not rejected, mean life could be
1500 hrs
7.5 CV = 1.83 TS= 2.87 H0 rejected, drug gives more hours
sleep
7.6 CV = 2.58 TS= 1.98 H0 not rejected, coin could be fair

7.7 CV = 1.89 TS= 1.70 H0 not rejected, training may be

ineffective
7.8 CV = 1.64 TS= 1.86 H0 rejected, could be less than 84
scoops
7.9 CV = 2.82 TS= 2.27 H0 not rejected, yields could be same

7.10 CV = 1.83 TS= 1.20 H0 not rejected, study has not been
effective
7.11 CV = 1.64 TS= 1.41 H0 not rejected, incidents not
increasing
7.12 CV = 2.45 TS= 2.05 H0 not rejected, interviewers not
different
7.13 CV = 1.64 TS= 1.73 H0 rejected, percentage lower than
60
7.14 CV = 2.62 TS= 2.15 H0 not rejected, mean load could be
10 tonnes
7.15 CV =2.45 TS=2.01 H0 not rejected, yields could be same

7.16 CV = 2.33 TS=1.17 H0 not rejected, claim of 70% upheld

7.17 CV = 1.75 TS=2.28 H0 rejected, increase in temperature

7.18 CV = 1.64 TS=2.07 H0 rejected, less than 70% will vote

labour
7.19 CV = 2.26 TS=0.67 H0 no t rejected, mean score could be
60%
7.20 CV = 1.73 TS=1.86 H0 rejected, method B better

7.21 CV = 1.96 TS=2.76 H0 rejected, The two groups not the

same
7.22 CV = 1.64 TS=3.0 H0 rejected, A could last longer than
B
7.23 CV = 2.33 TS=2.68 H0 rejected, Women get better mean
marks
7.24 CV = 2.33 TS=1.66 H0 not rejected, Brown quicker by 4
min.

CV= Critical value (Tabulated)

TS = Test Statistic (calculated value)